Automated Transcription of Neo-Latin Texts with Transkribus
Some good news for all “Digital Humanists”: The latest Transkribus model from our partners at the NOSCEMUS project is now out and available for all registered users of Transkribus, where it can be found under the name “Noscemus GM 2.2.” The model, trained and released by Stefan Zathammer, is based on training data from the project’s Digital Sourcebook and comprises at present (May 2020) around 1,600 fully corrected pages. Noscemus GM 2.2 is able to read texts set in Antiqua-based typefaces from the 15th, 16th, 17th and 18th century with a high level of accuracy and consistently outperforms most of the standard OCR engines. Although it is tailored towards transcribing (Neo-)Latin texts, Noscemus GM 2.2 also provides convincing results for other languages such as French, Italian and English. The Noscemus model is therefore able to offer help not only to Neo-Latinists, but to all kind of researchers dealing with larger text corpora from the Early Modern Period.
More information on the model are available at the Noscemus HP. For more information on the transcription tool “Transkribus” please have look at the webpage of the “Read” project.